© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7671
    Prev
    Next
    INDEX
    Explanations

    contrast with, believe it, seen ebrandvalue, win broader, lame not sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mani
    -0.09
    æīĢ以说
    -0.09
    å°±ç®Ĺ
    -0.08
    æĿ¡ä¾ĭ
    -0.08
    èī¯å¿ĥ
    -0.08
    æĬ¹
    -0.08
    æ¯ķç«Ł
    -0.08
    æĢ»çļĦæĿ¥è¯´
    -0.08
    å·¥ä½ľç»ıéªĮ
    -0.08
    就说
    -0.08
    POSITIVE LOGITS
     coach
    0.09
    coach
    0.09
    å±ģèĤ¡
    0.09
     coaching
    0.08
     Coach
    0.08
    é¢ĨåħĪ
    0.08
    ockets
    0.08
    çħľ
    0.08
    为客æĪ·
    0.08
    èĭ¥å¹²
    0.08
    Activations Density 0.353%

    No Known Activations